{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:19Z","timestamp":1760245039289,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1109\/devlrn.2014.6982985","type":"proceedings-article","created":{"date-parts":[[2014,12,30]],"date-time":"2014-12-30T23:48:19Z","timestamp":1419983299000},"page":"222-228","source":"Crossref","is-referenced-by-count":9,"title":["Inverse reinforcement learning using Dynamic Policy Programming"],"prefix":"10.1109","author":[{"given":"Eiji","family":"Uchibe","sequence":"first","affiliation":[]},{"given":"Kenji","family":"Doya","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E93.D.583"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"17","first-page":"3207","article-title":"Dynamic policy programming","volume":"13","author":"gheshlaghi azar","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"23","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc of the 16th International Conference on Machine Learning"},{"key":"18","first-page":"1391","article-title":"A least-squares approach to direct importance estimation","volume":"10","author":"kanamori","year":"2009","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Machine Learning A Probabilistic Perspective","year":"2012","author":"murphy","key":"24"},{"key":"15","first-page":"1016","article-title":"Inverse reinforcement learning through structured classification","volume":"25","author":"klein","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_1"},{"key":"13","article-title":"Relative entropy inverse reinforcement learning","volume":"15","author":"boularias","year":"2011","journal-title":"Proc of the International Conference on Artificial Intelligence and Statistics"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-014-0599-1"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094679"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630743"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00056-4"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139035613"},{"key":"2","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc of the 17th International Conference on Machine Learning"},{"journal-title":"Reinforcement Learning","year":"1998","author":"sutton","key":"1"},{"key":"10","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00007"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0710743106"},{"key":"5","article-title":"Inverse optimal control with linearly solvable MDPs","author":"dvijotham","year":"2010","journal-title":"Proc Of the 27th International Conference on Machine Learning"},{"key":"4","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proceedings of the 23rd AAAI Conference on Artificial Intelligence (AAAI"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5278-7"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907631"}],"event":{"name":"2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob)","start":{"date-parts":[[2014,10,13]]},"location":"Genoa, Italy","end":{"date-parts":[[2014,10,16]]}},"container-title":["4th International Conference on Development and Learning and on Epigenetic Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6971976\/6982939\/06982985.pdf?arnumber=6982985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:19:20Z","timestamp":1602688760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6982985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2014.6982985","relation":{},"subject":[],"published":{"date-parts":[[2014,10]]}}}